Bayesian Cramér-Rao Bound Estimation With Score-Based Models

Crafts, Evan Scope; Zhao, Bo

doi:10.1109/icassp49357.2023.10095110

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article1

Other1

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The posterior Cramér–Rao lower bound (PCRLB) serves as an indicator of the performance limit of an unbiased Bayesian estimator, which is widely used in the field of target tracking [1–6]. Commonly utilized in target tracking, direct discrete‐time kinematic models, like the discrete white noise acceleration (DWNA), the discrete Wiener process acceleration and the Singer models, are defined directly in discrete time [7].…”

Section: Introductionmentioning

confidence: 99%

PCRLB for batch discrete‐time estimation through state decoupling

Bao,

Luo

2024

Electronics Letters

View full text Add to dashboard Cite

This letter aims to obtain a closed‐form performance metric using the smoothing posterior Cramér–Rao lower bound (PCRLB) for a class of direct discrete‐time kinematic models. By decoupling the state‐space model into separate position, velocity and acceleration components using an independent dynamic representation, the velocity component in the a priori distribution is converted into a position component. Based on the above derivations, the closed‐form PCRLB is developed. The effectiveness of the proposed bound is demonstrated by contrasting the proposed smoothing PCRLB with the traditional recursive PCRLB in a bearings‐only target tracking scenario.

show abstract

Section: Introductionmentioning

confidence: 99%